langsmith 0.1.42 → 0.1.43

package/dist/client.cjs

@@ -1354,7 +1354,7 @@ class Client {
         const result = await response.json();
         return result;
     }
-    async createDataset(name, { description, dataType, } = {}) {
+    async createDataset(name, { description, dataType, inputsSchema, outputsSchema, } = {}) {
         const body = {
             name,
             description,
@@ -1362,6 +1362,12 @@ class Client {
         if (dataType) {
             body.data_type = dataType;
         }
+        if (inputsSchema) {
+            body.inputs_schema_definition = inputsSchema;
+        }
+        if (outputsSchema) {
+            body.outputs_schema_definition = outputsSchema;
+        }
         const response = await this.caller.call(fetch, `${this.apiUrl}/datasets`, {
             method: "POST",
             headers: { ...this.headers, "Content-Type": "application/json" },
@@ -1537,6 +1543,76 @@ class Client {
         }
         await response.json();
     }
+    async indexDataset({ datasetId, datasetName, tag, }) {
+        let datasetId_ = datasetId;
+        if (!datasetId_ && !datasetName) {
+            throw new Error("Must provide either datasetName or datasetId");
+        }
+        else if (datasetId_ && datasetName) {
+            throw new Error("Must provide either datasetName or datasetId, not both");
+        }
+        else if (!datasetId_) {
+            const dataset = await this.readDataset({ datasetName });
+            datasetId_ = dataset.id;
+        }
+        (0, _uuid_js_1.assertUuid)(datasetId_);
+        const data = {
+            tag: tag,
+        };
+        const response = await this.caller.call(fetch, `${this.apiUrl}/datasets/${datasetId_}/index`, {
+            method: "POST",
+            headers: { ...this.headers, "Content-Type": "application/json" },
+            body: JSON.stringify(data),
+            signal: AbortSignal.timeout(this.timeout_ms),
+            ...this.fetchOptions,
+        });
+        if (!response.ok) {
+            throw new Error(`Failed to index dataset ${datasetId_}: ${response.status} ${response.statusText}`);
+        }
+        await response.json();
+    }
+    /**
+     * Lets you run a similarity search query on a dataset.
+     *
+     * Requires the dataset to be indexed. Please see the `indexDataset` method to set up indexing.
+     *
+     * @param inputs      The input on which to run the similarity search. Must have the
+     *                    same schema as the dataset.
+     *
+     * @param datasetId   The dataset to search for similar examples.
+     *
+     * @param limit       The maximum number of examples to return. Will return the top `limit` most
+     *                    similar examples in order of most similar to least similar. If no similar
+     *                    examples are found, random examples will be returned.
+     *
+     * @returns           A list of similar examples.
+     *
+     *
+     * @example
+     * dataset_id = "123e4567-e89b-12d3-a456-426614174000"
+     * inputs = {"text": "How many people live in Berlin?"}
+     * limit = 5
+     * examples = await client.similarExamples(inputs, dataset_id, limit)
+     */
+    async similarExamples(inputs, datasetId, limit) {
+        const data = {
+            limit: limit,
+            inputs: inputs,
+        };
+        (0, _uuid_js_1.assertUuid)(datasetId);
+        const response = await this.caller.call(fetch, `${this.apiUrl}/datasets/${datasetId}/search`, {
+            method: "POST",
+            headers: { ...this.headers, "Content-Type": "application/json" },
+            body: JSON.stringify(data),
+            signal: AbortSignal.timeout(this.timeout_ms),
+            ...this.fetchOptions,
+        });
+        if (!response.ok) {
+            throw new Error(`Failed to fetch similar examples: ${response.status} ${response.statusText}`);
+        }
+        const result = await response.json();
+        return result["examples"];
+    }
     async createExample(inputs, outputs, { datasetId, datasetName, createdAt, exampleId, metadata, split, }) {
         let datasetId_ = datasetId;
         if (datasetId_ === undefined && datasetName === undefined) {

package/dist/client.d.ts

@@ -1,5 +1,5 @@
 import { AsyncCallerParams } from "./utils/async_caller.js";
-import { ComparativeExperiment, DataType, Dataset, DatasetDiffInfo, DatasetShareSchema, Example, ExampleUpdate, ExampleUpdateWithId, Feedback, FeedbackConfig, FeedbackIngestToken, KVMap, LangChainBaseMessage, LangSmithSettings, LikePromptResponse, Prompt, PromptCommit, PromptSortField, Run, RunCreate, RunUpdate, ScoreType, TimeDelta, TracerSession, TracerSessionResult, ValueType } from "./schemas.js";
+import { ComparativeExperiment, DataType, Dataset, DatasetDiffInfo, DatasetShareSchema, Example, ExampleUpdate, ExampleUpdateWithId, Feedback, FeedbackConfig, FeedbackIngestToken, KVMap, LangChainBaseMessage, LangSmithSettings, LikePromptResponse, Prompt, PromptCommit, PromptSortField, Run, RunCreate, RunUpdate, ScoreType, ExampleSearch, TimeDelta, TracerSession, TracerSessionResult, ValueType } from "./schemas.js";
 import { EvaluationResult, EvaluationResults, RunEvaluator } from "./evaluation/evaluator.js";
 interface ClientConfig {
     apiUrl?: string;
@@ -379,9 +379,11 @@ export declare class Client {
         projectName?: string;
     }): Promise<void>;
     uploadCsv({ csvFile, fileName, inputKeys, outputKeys, description, dataType, name, }: UploadCSVParams): Promise<Dataset>;
-    createDataset(name: string, { description, dataType, }?: {
+    createDataset(name: string, { description, dataType, inputsSchema, outputsSchema, }?: {
         description?: string;
         dataType?: DataType;
+        inputsSchema?: KVMap;
+        outputsSchema?: KVMap;
     }): Promise<Dataset>;
     readDataset({ datasetId, datasetName, }: {
         datasetId?: string;
@@ -423,6 +425,35 @@ export declare class Client {
         datasetId?: string;
         datasetName?: string;
     }): Promise<void>;
+    indexDataset({ datasetId, datasetName, tag, }: {
+        datasetId?: string;
+        datasetName?: string;
+        tag?: string;
+    }): Promise<void>;
+    /**
+     * Lets you run a similarity search query on a dataset.
+     *
+     * Requires the dataset to be indexed. Please see the `indexDataset` method to set up indexing.
+     *
+     * @param inputs      The input on which to run the similarity search. Must have the
+     *                    same schema as the dataset.
+     *
+     * @param datasetId   The dataset to search for similar examples.
+     *
+     * @param limit       The maximum number of examples to return. Will return the top `limit` most
+     *                    similar examples in order of most similar to least similar. If no similar
+     *                    examples are found, random examples will be returned.
+     *
+     * @returns           A list of similar examples.
+     *
+     *
+     * @example
+     * dataset_id = "123e4567-e89b-12d3-a456-426614174000"
+     * inputs = {"text": "How many people live in Berlin?"}
+     * limit = 5
+     * examples = await client.similarExamples(inputs, dataset_id, limit)
+     */
+    similarExamples(inputs: KVMap, datasetId: string, limit: number): Promise<ExampleSearch[]>;
     createExample(inputs: KVMap, outputs: KVMap, { datasetId, datasetName, createdAt, exampleId, metadata, split, }: CreateExampleOptions): Promise<Example>;
     createExamples(props: {
         inputs: Array<KVMap>;

package/dist/client.js

@@ -1327,7 +1327,7 @@ export class Client {
         const result = await response.json();
         return result;
     }
-    async createDataset(name, { description, dataType, } = {}) {
+    async createDataset(name, { description, dataType, inputsSchema, outputsSchema, } = {}) {
         const body = {
             name,
             description,
@@ -1335,6 +1335,12 @@ export class Client {
         if (dataType) {
             body.data_type = dataType;
         }
+        if (inputsSchema) {
+            body.inputs_schema_definition = inputsSchema;
+        }
+        if (outputsSchema) {
+            body.outputs_schema_definition = outputsSchema;
+        }
         const response = await this.caller.call(fetch, `${this.apiUrl}/datasets`, {
             method: "POST",
             headers: { ...this.headers, "Content-Type": "application/json" },
@@ -1510,6 +1516,76 @@ export class Client {
         }
         await response.json();
     }
+    async indexDataset({ datasetId, datasetName, tag, }) {
+        let datasetId_ = datasetId;
+        if (!datasetId_ && !datasetName) {
+            throw new Error("Must provide either datasetName or datasetId");
+        }
+        else if (datasetId_ && datasetName) {
+            throw new Error("Must provide either datasetName or datasetId, not both");
+        }
+        else if (!datasetId_) {
+            const dataset = await this.readDataset({ datasetName });
+            datasetId_ = dataset.id;
+        }
+        assertUuid(datasetId_);
+        const data = {
+            tag: tag,
+        };
+        const response = await this.caller.call(fetch, `${this.apiUrl}/datasets/${datasetId_}/index`, {
+            method: "POST",
+            headers: { ...this.headers, "Content-Type": "application/json" },
+            body: JSON.stringify(data),
+            signal: AbortSignal.timeout(this.timeout_ms),
+            ...this.fetchOptions,
+        });
+        if (!response.ok) {
+            throw new Error(`Failed to index dataset ${datasetId_}: ${response.status} ${response.statusText}`);
+        }
+        await response.json();
+    }
+    /**
+     * Lets you run a similarity search query on a dataset.
+     *
+     * Requires the dataset to be indexed. Please see the `indexDataset` method to set up indexing.
+     *
+     * @param inputs      The input on which to run the similarity search. Must have the
+     *                    same schema as the dataset.
+     *
+     * @param datasetId   The dataset to search for similar examples.
+     *
+     * @param limit       The maximum number of examples to return. Will return the top `limit` most
+     *                    similar examples in order of most similar to least similar. If no similar
+     *                    examples are found, random examples will be returned.
+     *
+     * @returns           A list of similar examples.
+     *
+     *
+     * @example
+     * dataset_id = "123e4567-e89b-12d3-a456-426614174000"
+     * inputs = {"text": "How many people live in Berlin?"}
+     * limit = 5
+     * examples = await client.similarExamples(inputs, dataset_id, limit)
+     */
+    async similarExamples(inputs, datasetId, limit) {
+        const data = {
+            limit: limit,
+            inputs: inputs,
+        };
+        assertUuid(datasetId);
+        const response = await this.caller.call(fetch, `${this.apiUrl}/datasets/${datasetId}/search`, {
+            method: "POST",
+            headers: { ...this.headers, "Content-Type": "application/json" },
+            body: JSON.stringify(data),
+            signal: AbortSignal.timeout(this.timeout_ms),
+            ...this.fetchOptions,
+        });
+        if (!response.ok) {
+            throw new Error(`Failed to fetch similar examples: ${response.status} ${response.statusText}`);
+        }
+        const result = await response.json();
+        return result["examples"];
+    }
     async createExample(inputs, outputs, { datasetId, datasetName, createdAt, exampleId, metadata, split, }) {
         let datasetId_ = datasetId;
         if (datasetId_ === undefined && datasetName === undefined) {

package/dist/index.cjs

@@ -6,4 +6,4 @@ Object.defineProperty(exports, "Client", { enumerable: true, get: function () {
 var run_trees_js_1 = require("./run_trees.cjs");
 Object.defineProperty(exports, "RunTree", { enumerable: true, get: function () { return run_trees_js_1.RunTree; } });
 // Update using yarn bump-version
-exports.__version__ = "0.1.42";
+exports.__version__ = "0.1.43";

package/dist/index.d.ts

@@ -1,4 +1,4 @@
 export { Client } from "./client.js";
 export type { Dataset, Example, TracerSession, Run, Feedback, RetrieverOutput, } from "./schemas.js";
 export { RunTree, type RunTreeConfig } from "./run_trees.js";
-export declare const __version__ = "0.1.42";
+export declare const __version__ = "0.1.43";

package/dist/index.js

@@ -1,4 +1,4 @@
 export { Client } from "./client.js";
 export { RunTree } from "./run_trees.js";
 // Update using yarn bump-version
-export const __version__ = "0.1.42";
+export const __version__ = "0.1.43";

package/dist/schemas.d.ts

@@ -181,6 +181,9 @@ export interface ExampleUpdate {
 export interface ExampleUpdateWithId extends ExampleUpdate {
     id: string;
 }
+export interface ExampleSearch extends BaseExample {
+    id: string;
+}
 export interface BaseDataset {
     name: string;
     description: string;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "langsmith",
-  "version": "0.1.42",
+  "version": "0.1.43",
   "description": "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform.",
   "packageManager": "yarn@1.22.19",
   "files": [